© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11465
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that start with the letters "ab", "be", "end", "sa", or contain categories of food or locations to eat

    oai_token-act-pair · gemini-2.0-flash

    technical or code-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    ab or be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.52
    EndProject
    -0.47
    Charter
    -0.46
     Charter
    -0.45
     nahilalakip
    -0.44
    charter
    -0.44
     Card
    -0.44
    Card
    -0.41
     reprises
    -0.41
    JspWriter
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.79
     propOrder
    0.68
    Tembelea
    0.66
     GenerationType
    0.65
    complexType
    0.60
     الحره
    0.58
    DeleteBehavior
    0.58
     Chwiliwch
    0.57
    hoga
    0.56
     Dostupné
    0.56
    Activations Density 0.662%

    No Known Activations